Update README.md

README.md

@@ -268,7 +268,7 @@ The model is based on VITS proposed by [Kim et al](https://arxiv.org/abs/2106.06
 | Lr. scheduler Disc                 | ExponentialLR                    |
 | Lr. scheduler Gamma Disc           | 0.999875                         |
 
-The model was trained for 91975 steps.
+The model was trained for 91,975 steps.
 
 The nos_fonemas formatter is a modification of the LJSpeech formatter with one extra column for the phonemized input.